memory_export

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint, so the description does not need to restate these. It adds the behavioral detail of an optional since/until window and reinforces the explicit_user_intent requirement, which is already in the schema. Beyond that, it does not disclose additional behaviors like error handling or output structure, so it adds modest value over the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no redundant wording. The primary action and formats are front-loaded, followed by the optional filter and use case. Every sentence contributes essential information without fluff, making it efficient and easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only export tool with no output schema, the description covers the core purpose, formats, time filtering, and the explicit intent requirement. It does not describe the exact return structure, but the formats imply the output shape, and annotations cover the safety profile. Minor gaps like pagination or size limits are absent, but they are not critical for a dump operation. Overall, it is sufficiently complete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters are already well-documented in the input schema. The description adds a high-level summary of the time window and formats, but these are already captured in the property descriptions. With full schema coverage, the baseline is 3, and the description does not introduce new parameter semantics beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool dumps the memory store in three specific formats (JSON, JSONL, Markdown) and supports optional time filtering. This distinguishes it from sibling tools like memory_get or memory_list, which are retrieval-focused, by emphasizing export for backup/inspection. The verb 'dump' and resource are explicit and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies the intended use case ('Use for backup/inspection') which gives clear context for when to invoke it. However, it does not explicitly mention alternatives or exclusion criteria (e.g., when to use memory_list instead), leaving some room for inference. The guidance is sufficient but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.